Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.53 Home All releases olderv2.1.52 v2.1.54newer
Claude Code v2.1.53

Background Agent Kill Notifications

When users kill running background agents (via the kill-agents shortcut), the system now sends a descriptive notification into the conversation.

Details
  • Single agent: Background agent "description" was killed by the user.
  • Multiple agents: N background agents were killed by the user: "desc1", "desc2".
  • Delivered as a task-notification mode message so the model understands context was interrupted
Evidence

Kill notification messages (search for "was killed by the user")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.53 →